Modelpublic

KYUNGYONG/aya-expanse-32b-abliterated-mlx-3Bit

sourceHugging Facecc-by-nc-4.0updated 1y agoView on Hugging Face

1likes58downloads

Model Card

KYUNGYONG/aya-expanse-32b-abliterated-mlx-3Bit

The Model KYUNGYONG/aya-expanse-32b-abliterated-mlx-3Bit was converted to MLX format from huihui-ai/aya-expanse-32b-abliterated using mlx-lm version 0.22.1.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("KYUNGYONG/aya-expanse-32b-abliterated-mlx-3Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)